seahorse-agent: Instructions file for Claude Code

CLAUDE.md

seahorse-agent CLAUDE.md is an instructions file for Claude Code from onceMisery/seahorse-agent. It costs 1,438 tokens per session, scanned A, original, Apache-2.0.

Project instructions for seahorse-agent, a Spring Boot platform that uses stored information to help generate answers and supports modular adapters and workflows.

In plain words
What is it for?
Use them when changing seahorse-agent's core, web or storage adapters, automatic setup, security, billing, knowledge-base, or workflow features.
Why use it?
They explain the project's modules and configuration order so an agent can work within its architecture.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is onceMisery/seahorse-agent's own configuration. It tells Claude Code how to work on seahorse-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything seahorse-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to onceMisery/seahorse-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/onceMisery/seahorse-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/onceMisery/seahorse-agent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for seahorse-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oncemisery/seahorse-agent/claude-md/github.svg)](https://agentmods.dev/instructions/oncemisery/seahorse-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/oncemisery/seahorse-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/oncemisery/seahorse-agent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for seahorse-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oncemisery/seahorse-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/oncemisery/seahorse-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,438 This file is loaded in full into every session.
When invoked 1,438 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01438 $0.01438
Opus 5 $0.00719 $0.00719
Sonnet 5 $0.00288 $0.00288
Haiku 4.5 $0.00144 $0.00144

Measured 10d ago against content hash a5bd338d9734, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

seahorse-agent CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Seahorse Agent 项目指南

项目概述

Seahorse Agent 是一个基于 Spring Boot 3.5.7 的 RAG(检索增强生成)智能体平台,采用六边形架构(端口-适配器模式)。

模块结构

seahorse-agent-kernel/              # 领域核心(L2)
seahorse-agent-adapter-web/         # Web 适配器(L3)
seahorse-agent-adapter-*/           # 各类适配器实现(L3)
seahorse-agent-spring-boot-starter/ # 自动配置(L3)
seahorse-agent-bootstrap/           # 启动入口
seahorse-agent-tests/               # 集成测试

自动配置架构

所有自动配置类注册在 AutoConfiguration.imports 中,分 13 层:

  1. Layer 0 — Multi-tenancy(after DataSource):租户隔离、RLS、TenantContext
  2. Layer 1 — Adapters(20 个,after DataSource):向量、缓存、存储、MQ、搜索等
  3. Layer 2 — Outbox relay(after MQ + Ops)
  4. Layer 3 — Native aggregator(after DataSource)
  5. Layer 4 — Kernel auth(after Auth adapter)
  6. Layer 5 — Kernel main(after Native aggregator)
  7. Layer 6 — Kernel sub-configs(16 个,after Kernel main + 各自依赖的 adapter)
  8. Layer 7 — Runtime guards(after kernel sub-configs)
  9. Layer 8 — Alert notification(after runtime guards):DingTalk 告警
  10. Layer 9 — Registration + Security:用户注册、BCrypt、安全加固
  11. Layer 10 — Billing:计费、订阅、配额强制
  12. Layer 11 — RAG + Workflow:高级 RAG、工作流可视化
  13. Layer 12 — KB + Marketplace + Admin:知识库增强、Agent 市场、管理后台
  14. Layer 13 — AOP + Health:权限切面、试用拦截器、Redis 健康检查

关键规则: kernel 子配置必须在 @AutoConfigureAfter 中声明所有产生 @ConditionalOnBean 依赖的 adapter/repository 配置。

Controller 模式

所有 Controller 使用 ObjectProvider<T> 懒加载:

private final ObjectProvider<SomePort> somePortProvider;

public SomeController(ObjectProvider<SomePort> somePortProvider) {
    this.somePortProvider = somePortProvider;  // 不要在这里调用 getIfAvailable()
}

@GetMapping("/api")
public Map<String, Object> api() {
    return Map.of("code", "0", "data", somePortProvider.getIfAvailable().query());
}

部署

全量部署(所有中间件)

docker compose -f docker-compose.full.yml up -d --build

包含:PostgreSQL + Redis + Milvus + Pulsar + Elasticsearch + MinIO

本地构建 + Docker 打包(推荐,避免 Maven 代理问题)

./mvnw package -B -pl seahorse-agent-bootstrap -am -DskipTests -Dspotless.check.skip=true
docker build -t seahorse-agent-backend:latest -f - . <<'EOF'
FROM eclipse-temurin:21-jre
WORKDIR /app
COPY seahorse-agent-bootstrap/target/seahorse-agent-bootstrap-0.0.1-SNAPSHOT-exec.jar app.jar
EXPOSE 9090
ENTRYPOINT ["java", "-jar", "app.jar"]
EOF
docker compose -f docker-compose.full.yml up -d backend

Read the full file on GitHub · 116 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 116 lines · 1,438 tokens per session scan A a5bd338d9734

Subscribe to this mod's changes

seahorse-agent CLAUDE.md is an instructions file published in the GitHub repository onceMisery/seahorse-agent (17 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,438 tokens to every session, about $0.0072 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens